Cross-domain Named Entity Recognition (NER) transfers the NER knowledge from high-resource domains to the low-resource target domain.
Specifically, considering that text modifier may refer to semantic concepts not existing in the reference image and requiring to be added into the target image, we learn the multi-modal concept alignment between the text modifier and the concatenation of reference and target images, under multiple-instance learning framework with image and sentence level weak supervision.
To address these problems, we propose a general language model distillation (GLMD) method that performs two-stage word prediction distillation and vocabulary compression, which is simple and surprisingly shows extremely strong performance.
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.
However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems.
In this paper, we propose a new task of aesthetic language assessment: aesthetic visual question and answering (AVQA) of images.
In recent years, image generation has made great strides in improving the quality of images, producing high-fidelity ones.
Knowledge graph embeddings (KGE) have been validated as powerful methods for inferring missing links in knowledge graphs (KGs) since they map entities into Euclidean space and treat relations as transformations of entities.
In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document.
In this paper, we propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets from LGE CMR images automatically and accurately in an end-to-end way.
The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods.
Paper-reviewer recommendation task is of significant academic importance for conference chairs and journal editors.
Based on the generated discriminative consistent domain, we can use the unlabeled data to learn the task model along with the labeled data via a consistent image generation.
The proposed DMQCA model consists of a multiview module with two attention mechanisms, a key-frame module, and a regression module, to achieve direct accurate multiple-index estimation.
Accurate detection of the myocardial infarction (MI) area is crucial for early diagnosis planning and follow-up management.